Attention-Mechanism-Based Models for Unconstrained Face Recognition with Mask Occlusion

Zhang, Mengya; Zhang, Yuan; Zhang, Qinghui

doi:10.3390/electronics12183916

Cited by 3 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies have made notable advancements. Zhang et al [13] improved the Inception module, significantly enhancing performance on datasets featuring masked faces. LIAAD [14] developed a novel, lightweight attentionbased method that, through knowledge distillation, improves accuracy and robustness against age variations in face recognition.…”

Section: Introductionmentioning

confidence: 99%

Face-Inception-Net for Recognition

Zhang,

Wang,

Zhang

et al. 2024

Electronics

Self Cite

View full text Add to dashboard Cite

Face recognition in general scenarios has been saturated in recent years, but there is still room to enhance model performance in extreme scenarios and fairness situations. Inspired by the successful application of Transformer and ConvNet in computer vision, we propose a FIN-Block, which gives a more flexible composition paradigm for building a novel pure convolution model and provides a foundation for constructing a new framework for general face recognition in both extreme scenarios and fairness situations. FIN-Block-A uses a combination of stacked large-size convolution kernels and parallel convolution branches to ensure a large spatial receptive field while improving the module’s deep feature embedding and extraction capabilities. FIN-Block-B takes advantage of stacked orthogonal convolution kernels and parallel branches to balance model size and performance. By applying FIN-Block with an adapted convolution kernel size in different stages, we built a reasonable and novel framework Face-Inception-Net, and the performance of the model is highly competitive with ConvNeXt and InceptionNeXt. The models were trained on CASIA-WebFace and MS-wo-RFW databases and evaluated on 14 mainstream benchmarks, including LFW, extreme scene, and fairness test sets. The proposed Face-Inception-Net achieved the highest average TAR@FAR0.001 of 95.9% in all used benchmarks, fully demonstrating effectiveness and generality in various scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

Face-Inception-Net for Recognition

Zhang,

Wang,

Zhang

et al. 2024

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

YOLOv7-based attention and improved feature fusion small object detection algorithm

Jingfeng Xiao,

Meng,

Wang

et al. 2024

Third International Conference on Computer Technology, Information Engineering, and Electron Materials (CTIEEM 2023)

View full text Add to dashboard Cite

In the current social environment, UAV detection technology has various applications in various fields, such as agricultural management, urban planning, and security monitoring. However, there are still problems, such as difficult localization and low accuracy in the UAV small target detection field. In this paper, for the problem of UAV small target detection, the characteristics of YOLOv7 model are sorted out and improved from several aspects, and the AED-YOLOv7 model is constructed. Aiming at the problem that multi-scale feature fusion in the model is prone to feature loss, this paper uses the FAM module, which reduces the spatial location variability of information between multiple scales and strengthens the feature fusion capability. This paper introduces the EMA module, which learns effective channel descriptions, generates better pixel-level attention for advanced feature mapping, and groups channel dimensions into multiple sub-features so that spatial semantic features are evenly distributed in each feature group. In this paper, we use Decoupled Head to process the classification and regression tasks separately, which can be better adapted to the needs of different tasks. Finally, this paper uses the EIoU Loss function to minimize the difference between the width and height of the target frame and the Anchor while retaining the beneficial properties of the CIoU Loss, which produces faster convergence and better localization results. On the VisDrone2019 benchmark, compared to the performance of YOLOv7, the AP50 of AED-YOLOv7 is improved by 3.5% and APS by 3.2%.

show abstract

Comparative Analysis of Measurement Tools in the Cognex D900 Vision System

Jancarczyk,

Rysiński,

Worek

2024

Applied Sciences

View full text Add to dashboard Cite

This paper presents a comprehensive comparative analysis of the measurement tools in the Cognex D900 vision system, applied within an industrial manufacturing environment focused on quality control. Initially, issues related to vision systems, including their definition, history, and development path, are discussed. The benefits of using vision systems in such industrial scenarios are presented. The analysis examines the operation of selected functions offered by the vision system, comparing two methods of program preparation for inspection: user-configured functions performing the indicated measurements and image analysis using deep learning. The first method allows for the omission of non-critical defects, providing specific dimension values for further analysis by other systems, and features straightforward function configuration with low hardware requirements, with modification times ranging from 30 to 200 ms depending on image detail placement. Conversely, the ViDi tool offers comprehensive image analysis without the need to specify detail features, enabling the detection of any deviations from a reference pattern. Through a series of tests conducted in a high-precision manufacturing environment, this research highlights the strengths, limitations, and practical implications of using advanced vision systems in automated inspection and quality control processes.

show abstract

Attention-Mechanism-Based Models for Unconstrained Face Recognition with Mask Occlusion

Cited by 3 publications

References 27 publications

Face-Inception-Net for Recognition

Face-Inception-Net for Recognition

YOLOv7-based attention and improved feature fusion small object detection algorithm

Comparative Analysis of Measurement Tools in the Cognex D900 Vision System

Contact Info

Product

Resources

About